Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization

The paper introduces a Database Normalization Benchmark (DNBENCH) with 3,275 samples to evaluate how well Large Language Models (LLMs) can perform database normalization from 1NF to BCNF, assessing semantic equivalence, structural accuracy, and logical validity. It identifies common failures in dependency inference, schema decomposition, and inter-table constraint reconstruction across various complexity levels. The authors also propose a Multi-Agent Reasoning for Schemas (MARS) framework that separates evidence extraction, violation diagnosis, and decomposition planning from schema generation, achieving an 82.0% improvement in DNB-SCORE over a single-prompt baseline.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms
• agents
• benchmarks